ChatGPT for Google Sheets exfiltrates workbooks

Turns out that some of the people building the software with AI have no clue how to secure them or even know it is riddled with security holes added by the AI.

Pure vibes.

Re: ChatGPT for Google Sheets exfiltrates workbooks

#5

Post by dakolli » Sun, May 31, 2026, 10:15 PM UTC

jonplackett wrote: post #2

So is your business model to expose AI security issues and then sell the solution?

Is that not every cyber consultancy? What's wrong with that?

Re: ChatGPT for Google Sheets exfiltrates workbooks

#6

Post by airstrike » Sun, May 31, 2026, 10:15 PM UTC

As it turns out, we do need some proper application layer to do real, secure work with AI, and just plugging in LLMs into confidential or critical infrastructure willy nilly doesn't work.

Re: ChatGPT for Google Sheets exfiltrates workbooks

#7

Post by simonw » Sun, May 31, 2026, 10:16 PM UTC

> This attack occurs when any untrusted data source (e.g., from an imported sheet or ChatGPT connector) manipulates ChatGPT to run an attacker-controlled external script, which executes leveraging permissions the user has granted to the ChatGPT for Google Sheets extension.

Yeah, I don't like the sound of that at all.

Re: ChatGPT for Google Sheets exfiltrates workbooks

#8

Post by dakolli » Sun, May 31, 2026, 10:16 PM UTC

rvz wrote: post #4

Turns out that some of the people building the software with AI have no clue how to secure them or even know it is riddled with security holes added by the AI. Pure vibes.

Even the people that do know better are so lazy now because of LLMs these things are happening at a rapid clip.The only thing that matters now is speed and chasing the dopamine dragon of pseudo productivity.

Re: ChatGPT for Google Sheets exfiltrates workbooks

#9

Post by milkshakes » Sun, May 31, 2026, 10:18 PM UTC

simonw wrote: post #7

> This attack occurs when any untrusted data source (e.g., from an imported sheet or ChatGPT connector) manipulates ChatGPT to run an attacker-controlled external script, which executes leveraging permissions the user has granted to the ChatGPT for Google Sheets extension. Yeah, I don't like the sound of that at all.

it looks like the key to this working is the user explicitly directing the model to run those instructions. in this case it is the user, not the model that is being manipulated

> Please follow the step-by-step workflow in the comp sheet to update my model with data thru F29

Re: ChatGPT for Google Sheets exfiltrates workbooks

#10

Post by grim_io » Sun, May 31, 2026, 10:19 PM UTC

rvz wrote: post #4

Turns out that some of the people building the software with AI have no clue how to secure them or even know it is riddled with security holes added by the AI. Pure vibes.

I don't think anyone is surprised by it. People are not vibe-coding zombies... yet.

It's a matter of one trillion-dollar company not falling behind another trillion-dollar company. They know what they are doing and are OK with it.